pipeline-review

pipeline-review is a skill for Claude Code from OneWave-AI/open-agent-stack. It costs 40 tokens per session (435 once invoked), scanned A, original, MIT.

A weekly review of sales opportunities in a CRM, which is software for tracking potential deals, or in an exported deal list.

In plain words
What is it for?
It helps flag inactive opportunities, assign one next action to each open deal, separate likely revenue from weak leads, and identify deals to close.
Why use it?
It reveals stalled deals, missing next steps, and forecasts that are more hopeful than the evidence supports.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the sales-desk plugin — 4 skills shipped together

Good fit It helps flag inactive opportunities, assign one next action to each open deal, separate likely revenue from weak leads, and identify deals to close.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/onewave-ai/open-agent-stack/pipeline-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add OneWave-AI/open-agent-stack --skill pipeline-review
Clone the repo
git clone --depth 1 https://github.com/OneWave-AI/open-agent-stack

Made for: Claude Code.

Or install sales-desk, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pipeline-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/pipeline-review/github.svg)](https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review)
Your own site
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/pipeline-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pipeline-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/pipeline-review"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/pipeline-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 435 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00040 $0.00435
Opus 5 $0.00020 $0.00217
Sonnet 5 $0.00008 $0.00087
Haiku 4.5 $0.00004 $0.00044

Measured 8d ago against content hash 2f28c4421d5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pipeline-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sales-desk/skills/pipeline-review/SKILL.md · 24 lines

What it actually says

Pipeline Review

A pipeline review answers three questions per deal: is it real, is it moving, and what happens next. Input: CRM pipeline (via connected MCP) or a pasted/exported deal list with stages, amounts, and last-activity dates.

Workflow

  1. Staleness sweep. Flag every deal with no activity beyond its stage's normal rhythm (default: 14 days early-stage, 7 days late-stage). Sort by amount -- the biggest quiet deal is the headline.
  2. Next-action audit. Every open deal gets exactly one named next action with an owner and a date. Deals where the next action is "waiting on them" get a nudge drafted; deals where nobody can name a next action get flagged as not-real candidates.
  3. Honest forecast. Split the pipeline: commit (verbal yes or contract out), probable (champion engaged, process defined), possible (interest without process), and hope (everything else). Report the gap between quota and commit+probable -- that gap is the week's real to-do list.
  4. The kill list. Deals stalled past two cycles with no champion and no process: recommend closing them out. A pipeline padded with dead deals hides the real gap until it is too late to fix.
  5. Output. One-page review: headline risks, the stalled list with unstick moves per deal, the forecast split, and the five actions that most change this quarter's number.

Rules

  • Last-activity date is the truth serum -- what the rep says about a deal matters less than when the buyer last did anything.
  • "Hope" is a category, not an insult; it just does not forecast.
  • Every recommendation is an action with a name on it, not an observation.
  • Track review over review: deals that were stalled last week and are stalled this week escalate automatically.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 24 lines · 40 tokens per session scan A 2f28c4421d5c

Subscribe to this mod's changes

pipeline-review is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 28d ago), licensed MIT. It adds 40 tokens to every session and 435 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.